Upload main.log with huggingface_hub
Browse files
main.log
CHANGED
|
@@ -108,3 +108,60 @@ s:103 trl:7.0698 lr:0.000089 norm:0.76
|
|
| 108 |
s:104 trl:7.0406 lr:0.000090 norm:0.96
|
| 109 |
s:105 trl:7.0250 lr:0.000091 norm:1.63
|
| 110 |
s:106 trl:7.0482 lr:0.000092 norm:1.34
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 108 |
s:104 trl:7.0406 lr:0.000090 norm:0.96
|
| 109 |
s:105 trl:7.0250 lr:0.000091 norm:1.63
|
| 110 |
s:106 trl:7.0482 lr:0.000092 norm:1.34
|
| 111 |
+
s:107 trl:7.0078 lr:0.000093 norm:1.06
|
| 112 |
+
s:108 trl:6.9675 lr:0.000093 norm:1.08
|
| 113 |
+
s:109 trl:7.0259 lr:0.000094 norm:0.68
|
| 114 |
+
s:110 trl:6.9906 lr:0.000095 norm:0.83
|
| 115 |
+
s:111 trl:6.9863 lr:0.000096 norm:0.81
|
| 116 |
+
s:112 trl:6.9761 lr:0.000097 norm:0.88
|
| 117 |
+
s:113 trl:6.8700 lr:0.000098 norm:1.18
|
| 118 |
+
s:114 trl:6.8831 lr:0.000099 norm:0.99
|
| 119 |
+
s:115 trl:6.9047 lr:0.000099 norm:0.67
|
| 120 |
+
s:116 trl:6.8666 lr:0.000100 norm:0.60
|
| 121 |
+
s:117 trl:6.9040 lr:0.000101 norm:0.63
|
| 122 |
+
s:118 trl:6.8626 lr:0.000102 norm:0.67
|
| 123 |
+
s:119 trl:6.8275 lr:0.000103 norm:0.92
|
| 124 |
+
s:120 trl:6.8329 lr:0.000104 norm:1.05
|
| 125 |
+
s:121 trl:6.8539 lr:0.000105 norm:0.94
|
| 126 |
+
s:122 trl:6.8529 lr:0.000105 norm:0.84
|
| 127 |
+
s:123 trl:6.8346 lr:0.000106 norm:1.22
|
| 128 |
+
s:124 trl:6.8622 lr:0.000107 norm:2.00
|
| 129 |
+
s:125 trl:6.8591 lr:0.000108 norm:0.86
|
| 130 |
+
s:126 trl:6.8507 lr:0.000109 norm:3.04
|
| 131 |
+
s:127 trl:6.8790 lr:0.000110 norm:1.35
|
| 132 |
+
s:128 trl:6.8390 lr:0.000111 norm:1.92
|
| 133 |
+
s:129 trl:6.7976 lr:0.000111 norm:1.55
|
| 134 |
+
s:130 trl:6.7552 lr:0.000112 norm:0.89
|
| 135 |
+
s:131 trl:6.8026 lr:0.000113 norm:1.47
|
| 136 |
+
s:132 trl:6.8292 lr:0.000114 norm:0.93
|
| 137 |
+
s:133 trl:6.7605 lr:0.000115 norm:0.94
|
| 138 |
+
s:134 trl:6.7320 lr:0.000116 norm:1.11
|
| 139 |
+
s:135 trl:6.6809 lr:0.000117 norm:0.98
|
| 140 |
+
s:136 trl:6.7129 lr:0.000117 norm:1.02
|
| 141 |
+
s:137 trl:6.6902 lr:0.000118 norm:0.96
|
| 142 |
+
s:138 trl:6.6102 lr:0.000119 norm:0.97
|
| 143 |
+
s:139 trl:6.6275 lr:0.000120 norm:0.75
|
| 144 |
+
s:140 trl:6.6287 lr:0.000121 norm:0.97
|
| 145 |
+
s:141 trl:6.6448 lr:0.000122 norm:0.90
|
| 146 |
+
s:142 trl:6.6683 lr:0.000123 norm:0.53
|
| 147 |
+
s:143 trl:6.5854 lr:0.000123 norm:0.73
|
| 148 |
+
s:144 trl:6.6075 lr:0.000124 norm:0.68
|
| 149 |
+
s:145 trl:6.6085 lr:0.000125 norm:0.74
|
| 150 |
+
s:146 trl:6.6008 lr:0.000126 norm:0.69
|
| 151 |
+
s:147 trl:6.6363 lr:0.000127 norm:0.75
|
| 152 |
+
s:148 trl:6.6122 lr:0.000128 norm:0.92
|
| 153 |
+
s:149 trl:6.6019 lr:0.000129 norm:0.95
|
| 154 |
+
s:150 tel:6.6575
|
| 155 |
+
s:150 trl:6.6008 lr:0.000129 norm:0.82
|
| 156 |
+
s:151 trl:6.5701 lr:0.000130 norm:1.02
|
| 157 |
+
s:152 trl:6.5381 lr:0.000131 norm:0.99
|
| 158 |
+
s:153 trl:6.5604 lr:0.000132 norm:1.09
|
| 159 |
+
s:154 trl:6.5890 lr:0.000133 norm:0.87
|
| 160 |
+
s:155 trl:6.5826 lr:0.000134 norm:0.80
|
| 161 |
+
s:156 trl:6.5699 lr:0.000135 norm:0.69
|
| 162 |
+
s:157 trl:6.5194 lr:0.000135 norm:0.74
|
| 163 |
+
s:158 trl:6.5117 lr:0.000136 norm:0.85
|
| 164 |
+
s:159 trl:6.5268 lr:0.000137 norm:0.83
|
| 165 |
+
s:160 trl:6.5390 lr:0.000138 norm:0.61
|
| 166 |
+
s:161 trl:6.5418 lr:0.000139 norm:0.82
|
| 167 |
+
s:162 trl:6.4409 lr:0.000140 norm:1.09
|